Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases related to support and improvement in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ibia
    -0.16
    isci
    -0.15
    нож
    -0.15
    .Accessible
    -0.15
    æļ
    -0.14
    tainment
    -0.14
    alli
    -0.14
    ongan
    -0.14
    baugh
    -0.14
    ugh
    -0.14
    POSITIVE LOGITS
    ostel
    0.17
     Vladim
    0.16
    708
    0.16
    ija
    0.16
    idar
    0.15
    TypeId
    0.15
    wise
    0.14
    oster
    0.14
    usch
    0.14
    ãĥªãĤ«
    0.14
    Act Density 0.171%

    No Known Activations